agent-browser

Automate web navigation, interaction, data extraction, and performance profiling for browsers.

5|2|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/scottopell/phoenix-ide --skill agent-browser-scottopell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/scottopell/phoenix-ide/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/scottopell/phoenix-ide --skill agent-browser-scottopell

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Automates complex browser tasks such as navigation, interaction, data extraction, and testing, reducing manual effort and increasing reliability.

Core Features & Use Cases

  • Web Automation: Navigate to websites, fill forms, click buttons, and perform interactions automatically.
  • Data Extraction: Retrieve text, HTML, screenshots, and generate PDFs from web pages.
  • Use Case: Automate login to a site, scrape data, and generate reports without manual browser handling.
  • Testing & Debugging: Take videos, record sessions, and profile page performance for QA purposes. Imagine reducing manual testing hours by recording sessions and extracting structured data efficiently.

Quick Start

Describe navigating to a site, filling out a form, and capturing a screenshot to assist an AI in executing the automation in one command.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping and form interactions in headless mode?

Web automation in headless mode lets you programmatically navigate sites, fill forms, and extract data without manual browser handling. This Skill automates these interactions, supporting multiple sessions for efficient, reliable content retrieval.

What is browser automation for performance profiling and QA testing?

Browser automation for performance profiling records sessions and captures page metrics during automated interactions. This Skill enables QA teams to take videos and profile page performance, reducing manual testing hours by extracting structured data efficiently.

How do I manage sessions, cookies, and authentication states for automated testing?

Managing sessions, cookies, and authentication states for automated testing uses secure save and load mechanisms. This Skill ensures reliable handling of authentication states across multiple browser sessions for continuous web automation workflows.

Can I generate PDFs and capture screenshots during web scraping workflows?

Generating PDFs and capturing screenshots during web scraping workflows is fully supported as a data extraction feature. You can retrieve text, HTML, and visual assets from web pages to automate reporting without manual browser intervention.

Does headless browser automation work with existing development and QA pipelines?

Headless browser automation integrates directly with existing development and QA pipelines. This Skill streamlines workflows including navigation, interaction, data retrieval, and performance profiling, fitting seamlessly into automated testing environments.

What is the best way to extract structured data from web pages without manual browser handling?

The best way to extract structured data without manual browser handling is through automated navigation and interaction. This Skill retrieves text, HTML, and screenshots, enabling you to automate logins, scrape data, and generate reports efficiently.